public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
* [PATCH] RISC-V: Add RVV machine modes.
@ 2022-09-15 11:39 juzhe.zhong
  2022-09-23 15:45 ` Kito Cheng
  0 siblings, 1 reply; 3+ messages in thread
From: juzhe.zhong @ 2022-09-15 11:39 UTC (permalink / raw)
  To: gcc-patches; +Cc: kito.cheng, palmer, zhongjuzhe

From: zhongjuzhe <juzhe.zhong@rivai.ai>

gcc/ChangeLog:

        * config/riscv/riscv-modes.def (VECTOR_BOOL_MODE): Add RVV mask modes.
        (ADJUST_NUNITS): Adjust nunits using riscv_vector_chunks.
        (ADJUST_ALIGNMENT): Adjust alignment.
        (ADJUST_BYTESIZE): Adjust bytesize using riscv_vector_chunks.
        (RVV_MODES): New macro.
        (VECTOR_MODE_WITH_PREFIX): Add RVV vector modes.
        (VECTOR_MODES_WITH_PREFIX): Add RVV vector modes.

---
 gcc/config/riscv/riscv-modes.def | 141 +++++++++++++++++++++++++++++++
 1 file changed, 141 insertions(+)

diff --git a/gcc/config/riscv/riscv-modes.def b/gcc/config/riscv/riscv-modes.def
index 6e30c1a5595..95f69e87e23 100644
--- a/gcc/config/riscv/riscv-modes.def
+++ b/gcc/config/riscv/riscv-modes.def
@@ -22,6 +22,147 @@ along with GCC; see the file COPYING3.  If not see
 FLOAT_MODE (HF, 2, ieee_half_format);
 FLOAT_MODE (TF, 16, ieee_quad_format);
 
+/* Vector modes.  */
+
+/* Encode the ratio of SEW/LMUL into the mask types. There are the following
+ * mask types.  */
+
+/* | Mode     | MIN_VLEN = 32 | MIN_VLEN = 64 |
+   |          | SEW/LMUL      | SEW/LMUL      |
+   | VNx1BI   | 32            | 64            |
+   | VNx2BI   | 16            | 32            |
+   | VNx4BI   | 8             | 16            |
+   | VNx8BI   | 4             | 8             |
+   | VNx16BI  | 2             | 4             |
+   | VNx32BI  | 1             | 2             |
+   | VNx64BI  | N/A           | 1             |  */
+
+VECTOR_BOOL_MODE (VNx1BI, 1, BI, 8);
+VECTOR_BOOL_MODE (VNx2BI, 2, BI, 8);
+VECTOR_BOOL_MODE (VNx4BI, 4, BI, 8);
+VECTOR_BOOL_MODE (VNx8BI, 8, BI, 8);
+VECTOR_BOOL_MODE (VNx16BI, 16, BI, 8);
+VECTOR_BOOL_MODE (VNx32BI, 32, BI, 8);
+VECTOR_BOOL_MODE (VNx64BI, 64, BI, 8);
+
+ADJUST_NUNITS (VNx1BI, riscv_vector_chunks * 1);
+ADJUST_NUNITS (VNx2BI, riscv_vector_chunks * 2);
+ADJUST_NUNITS (VNx4BI, riscv_vector_chunks * 4);
+ADJUST_NUNITS (VNx8BI, riscv_vector_chunks * 8);
+ADJUST_NUNITS (VNx16BI, riscv_vector_chunks * 16);
+ADJUST_NUNITS (VNx32BI, riscv_vector_chunks * 32);
+ADJUST_NUNITS (VNx64BI, riscv_vector_chunks * 64);
+
+ADJUST_ALIGNMENT (VNx1BI, 1);
+ADJUST_ALIGNMENT (VNx2BI, 1);
+ADJUST_ALIGNMENT (VNx4BI, 1);
+ADJUST_ALIGNMENT (VNx8BI, 1);
+ADJUST_ALIGNMENT (VNx16BI, 1);
+ADJUST_ALIGNMENT (VNx32BI, 1);
+ADJUST_ALIGNMENT (VNx64BI, 1);
+
+ADJUST_BYTESIZE (VNx1BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx2BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx4BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx8BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx16BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx32BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx64BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
+
+/*
+   | Mode        | MIN_VLEN=32 | MIN_VLEN=32 | MIN_VLEN=64 | MIN_VLEN=64 |
+   |             | LMUL        |  SEW/LMUL   | LMUL        | SEW/LMUL    |
+   | VNx1QI      | MF4         |  32         | MF8         | 64          |
+   | VNx2QI      | MF2         |  16         | MF4         | 32          |
+   | VNx4QI      | M1          |  8          | MF2         | 16          |
+   | VNx8QI      | M2          |  4          | M1          | 8           |
+   | VNx16QI     | M4          |  2          | M2          | 4           |
+   | VNx32QI     | M8          |  1          | M4          | 2           |
+   | VNx64QI     | N/A         |  N/A        | M8          | 1           |
+   | VNx1(HI|HF) | MF2         |  32         | MF4         | 64          |
+   | VNx2(HI|HF) | M1          |  16         | MF2         | 32          |
+   | VNx4(HI|HF) | M2          |  8          | M1          | 16          |
+   | VNx8(HI|HF) | M4          |  4          | M2          | 8           |
+   | VNx16(HI|HF)| M8          |  2          | M4          | 4           |
+   | VNx32(HI|HF)| N/A         |  N/A        | M8          | 2           |
+   | VNx1(SI|SF) | M1          |  32         | MF2         | 64          |
+   | VNx2(SI|SF) | M2          |  16         | M1          | 32          |
+   | VNx4(SI|SF) | M4          |  8          | M2          | 16          |
+   | VNx8(SI|SF) | M8          |  4          | M4          | 8           |
+   | VNx16(SI|SF)| N/A         |  N/A        | M8          | 4           |
+   | VNx1(DI|DF) | N/A         |  N/A        | M1          | 64          |
+   | VNx2(DI|DF) | N/A         |  N/A        | M2          | 32          |
+   | VNx4(DI|DF) | N/A         |  N/A        | M4          | 16          |
+   | VNx8(DI|DF) | N/A         |  N/A        | M8          | 8           |
+*/
+
+/* Define RVV modes whose sizes are multiples of 64-bit chunks.  */
+#define RVV_MODES(NVECS, VB, VH, VS, VD)                                       \
+  VECTOR_MODES_WITH_PREFIX (VNx, INT, 8 * NVECS, 0);                           \
+  VECTOR_MODES_WITH_PREFIX (VNx, FLOAT, 8 * NVECS, 0);                         \
+                                                                               \
+  ADJUST_NUNITS (VB##QI, riscv_vector_chunks * NVECS * 8);                     \
+  ADJUST_NUNITS (VH##HI, riscv_vector_chunks * NVECS * 4);                     \
+  ADJUST_NUNITS (VS##SI, riscv_vector_chunks * NVECS * 2);                     \
+  ADJUST_NUNITS (VD##DI, riscv_vector_chunks * NVECS);                         \
+  ADJUST_NUNITS (VH##HF, riscv_vector_chunks * NVECS * 4);                     \
+  ADJUST_NUNITS (VS##SF, riscv_vector_chunks * NVECS * 2);                     \
+  ADJUST_NUNITS (VD##DF, riscv_vector_chunks * NVECS);                         \
+                                                                               \
+  ADJUST_ALIGNMENT (VB##QI, 1);                                                \
+  ADJUST_ALIGNMENT (VH##HI, 2);                                                \
+  ADJUST_ALIGNMENT (VS##SI, 4);                                                \
+  ADJUST_ALIGNMENT (VD##DI, 8);                                                \
+  ADJUST_ALIGNMENT (VH##HF, 2);                                                \
+  ADJUST_ALIGNMENT (VS##SF, 4);                                                \
+  ADJUST_ALIGNMENT (VD##DF, 8);
+
+/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
+   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1DImode and VNx1DFmode.  */
+VECTOR_MODE_WITH_PREFIX (VNx, INT, DI, 1, 0);
+VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, DF, 1, 0);
+RVV_MODES (1, VNx8, VNx4, VNx2, VNx1)
+RVV_MODES (2, VNx16, VNx8, VNx4, VNx2)
+RVV_MODES (4, VNx32, VNx16, VNx8, VNx4)
+RVV_MODES (8, VNx64, VNx32, VNx16, VNx8)
+
+VECTOR_MODES_WITH_PREFIX (VNx, INT, 4, 0);
+VECTOR_MODES_WITH_PREFIX (VNx, FLOAT, 4, 0);
+ADJUST_NUNITS (VNx4QI, riscv_vector_chunks * 4);
+ADJUST_NUNITS (VNx2HI, riscv_vector_chunks * 2);
+ADJUST_NUNITS (VNx2HF, riscv_vector_chunks * 2);
+ADJUST_ALIGNMENT (VNx4QI, 1);
+ADJUST_ALIGNMENT (VNx2HI, 2);
+ADJUST_ALIGNMENT (VNx2HF, 2);
+
+/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
+   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1SImode and VNx1SFmode.  */
+VECTOR_MODE_WITH_PREFIX (VNx, INT, SI, 1, 0);
+VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, SF, 1, 0);
+ADJUST_NUNITS (VNx1SI, riscv_vector_chunks);
+ADJUST_NUNITS (VNx1SF, riscv_vector_chunks);
+ADJUST_ALIGNMENT (VNx1SI, 4);
+ADJUST_ALIGNMENT (VNx1SF, 4);
+
+VECTOR_MODES_WITH_PREFIX (VNx, INT, 2, 0);
+ADJUST_NUNITS (VNx2QI, riscv_vector_chunks * 2);
+ADJUST_ALIGNMENT (VNx2QI, 1);
+
+/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
+   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1HImode and VNx1HFmode.  */
+VECTOR_MODE_WITH_PREFIX (VNx, INT, HI, 1, 0);
+VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, HF, 1, 0);
+ADJUST_NUNITS (VNx1HI, riscv_vector_chunks);
+ADJUST_NUNITS (VNx1HF, riscv_vector_chunks);
+ADJUST_ALIGNMENT (VNx1HI, 2);
+ADJUST_ALIGNMENT (VNx1HF, 2);
+
+/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
+   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1QImode.  */
+VECTOR_MODE_WITH_PREFIX (VNx, INT, QI, 1, 0);
+ADJUST_NUNITS (VNx1QI, riscv_vector_chunks);
+ADJUST_ALIGNMENT (VNx1QI, 1);
+
 /* TODO: According to RISC-V 'V' ISA spec, the maximun vector length can
    be 65536 for a single vector register which means the vector mode in
    GCC can be maximum = 65536 * 8 bits (LMUL=8).
-- 
2.36.1


^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH] RISC-V: Add RVV machine modes.
  2022-09-15 11:39 [PATCH] RISC-V: Add RVV machine modes juzhe.zhong
@ 2022-09-23 15:45 ` Kito Cheng
  0 siblings, 0 replies; 3+ messages in thread
From: Kito Cheng @ 2022-09-23 15:45 UTC (permalink / raw)
  To: juzhe.zhong; +Cc: GCC Patches

Committed, thanks!

On Thu, Sep 15, 2022 at 7:40 PM <juzhe.zhong@rivai.ai> wrote:
>
> From: zhongjuzhe <juzhe.zhong@rivai.ai>
>
> gcc/ChangeLog:
>
>         * config/riscv/riscv-modes.def (VECTOR_BOOL_MODE): Add RVV mask modes.
>         (ADJUST_NUNITS): Adjust nunits using riscv_vector_chunks.
>         (ADJUST_ALIGNMENT): Adjust alignment.
>         (ADJUST_BYTESIZE): Adjust bytesize using riscv_vector_chunks.
>         (RVV_MODES): New macro.
>         (VECTOR_MODE_WITH_PREFIX): Add RVV vector modes.
>         (VECTOR_MODES_WITH_PREFIX): Add RVV vector modes.
>
> ---
>  gcc/config/riscv/riscv-modes.def | 141 +++++++++++++++++++++++++++++++
>  1 file changed, 141 insertions(+)
>
> diff --git a/gcc/config/riscv/riscv-modes.def b/gcc/config/riscv/riscv-modes.def
> index 6e30c1a5595..95f69e87e23 100644
> --- a/gcc/config/riscv/riscv-modes.def
> +++ b/gcc/config/riscv/riscv-modes.def
> @@ -22,6 +22,147 @@ along with GCC; see the file COPYING3.  If not see
>  FLOAT_MODE (HF, 2, ieee_half_format);
>  FLOAT_MODE (TF, 16, ieee_quad_format);
>
> +/* Vector modes.  */
> +
> +/* Encode the ratio of SEW/LMUL into the mask types. There are the following
> + * mask types.  */
> +
> +/* | Mode     | MIN_VLEN = 32 | MIN_VLEN = 64 |
> +   |          | SEW/LMUL      | SEW/LMUL      |
> +   | VNx1BI   | 32            | 64            |
> +   | VNx2BI   | 16            | 32            |
> +   | VNx4BI   | 8             | 16            |
> +   | VNx8BI   | 4             | 8             |
> +   | VNx16BI  | 2             | 4             |
> +   | VNx32BI  | 1             | 2             |
> +   | VNx64BI  | N/A           | 1             |  */
> +
> +VECTOR_BOOL_MODE (VNx1BI, 1, BI, 8);
> +VECTOR_BOOL_MODE (VNx2BI, 2, BI, 8);
> +VECTOR_BOOL_MODE (VNx4BI, 4, BI, 8);
> +VECTOR_BOOL_MODE (VNx8BI, 8, BI, 8);
> +VECTOR_BOOL_MODE (VNx16BI, 16, BI, 8);
> +VECTOR_BOOL_MODE (VNx32BI, 32, BI, 8);
> +VECTOR_BOOL_MODE (VNx64BI, 64, BI, 8);
> +
> +ADJUST_NUNITS (VNx1BI, riscv_vector_chunks * 1);
> +ADJUST_NUNITS (VNx2BI, riscv_vector_chunks * 2);
> +ADJUST_NUNITS (VNx4BI, riscv_vector_chunks * 4);
> +ADJUST_NUNITS (VNx8BI, riscv_vector_chunks * 8);
> +ADJUST_NUNITS (VNx16BI, riscv_vector_chunks * 16);
> +ADJUST_NUNITS (VNx32BI, riscv_vector_chunks * 32);
> +ADJUST_NUNITS (VNx64BI, riscv_vector_chunks * 64);
> +
> +ADJUST_ALIGNMENT (VNx1BI, 1);
> +ADJUST_ALIGNMENT (VNx2BI, 1);
> +ADJUST_ALIGNMENT (VNx4BI, 1);
> +ADJUST_ALIGNMENT (VNx8BI, 1);
> +ADJUST_ALIGNMENT (VNx16BI, 1);
> +ADJUST_ALIGNMENT (VNx32BI, 1);
> +ADJUST_ALIGNMENT (VNx64BI, 1);
> +
> +ADJUST_BYTESIZE (VNx1BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
> +ADJUST_BYTESIZE (VNx2BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
> +ADJUST_BYTESIZE (VNx4BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
> +ADJUST_BYTESIZE (VNx8BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
> +ADJUST_BYTESIZE (VNx16BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
> +ADJUST_BYTESIZE (VNx32BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
> +ADJUST_BYTESIZE (VNx64BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
> +
> +/*
> +   | Mode        | MIN_VLEN=32 | MIN_VLEN=32 | MIN_VLEN=64 | MIN_VLEN=64 |
> +   |             | LMUL        |  SEW/LMUL   | LMUL        | SEW/LMUL    |
> +   | VNx1QI      | MF4         |  32         | MF8         | 64          |
> +   | VNx2QI      | MF2         |  16         | MF4         | 32          |
> +   | VNx4QI      | M1          |  8          | MF2         | 16          |
> +   | VNx8QI      | M2          |  4          | M1          | 8           |
> +   | VNx16QI     | M4          |  2          | M2          | 4           |
> +   | VNx32QI     | M8          |  1          | M4          | 2           |
> +   | VNx64QI     | N/A         |  N/A        | M8          | 1           |
> +   | VNx1(HI|HF) | MF2         |  32         | MF4         | 64          |
> +   | VNx2(HI|HF) | M1          |  16         | MF2         | 32          |
> +   | VNx4(HI|HF) | M2          |  8          | M1          | 16          |
> +   | VNx8(HI|HF) | M4          |  4          | M2          | 8           |
> +   | VNx16(HI|HF)| M8          |  2          | M4          | 4           |
> +   | VNx32(HI|HF)| N/A         |  N/A        | M8          | 2           |
> +   | VNx1(SI|SF) | M1          |  32         | MF2         | 64          |
> +   | VNx2(SI|SF) | M2          |  16         | M1          | 32          |
> +   | VNx4(SI|SF) | M4          |  8          | M2          | 16          |
> +   | VNx8(SI|SF) | M8          |  4          | M4          | 8           |
> +   | VNx16(SI|SF)| N/A         |  N/A        | M8          | 4           |
> +   | VNx1(DI|DF) | N/A         |  N/A        | M1          | 64          |
> +   | VNx2(DI|DF) | N/A         |  N/A        | M2          | 32          |
> +   | VNx4(DI|DF) | N/A         |  N/A        | M4          | 16          |
> +   | VNx8(DI|DF) | N/A         |  N/A        | M8          | 8           |
> +*/
> +
> +/* Define RVV modes whose sizes are multiples of 64-bit chunks.  */
> +#define RVV_MODES(NVECS, VB, VH, VS, VD)                                       \
> +  VECTOR_MODES_WITH_PREFIX (VNx, INT, 8 * NVECS, 0);                           \
> +  VECTOR_MODES_WITH_PREFIX (VNx, FLOAT, 8 * NVECS, 0);                         \
> +                                                                               \
> +  ADJUST_NUNITS (VB##QI, riscv_vector_chunks * NVECS * 8);                     \
> +  ADJUST_NUNITS (VH##HI, riscv_vector_chunks * NVECS * 4);                     \
> +  ADJUST_NUNITS (VS##SI, riscv_vector_chunks * NVECS * 2);                     \
> +  ADJUST_NUNITS (VD##DI, riscv_vector_chunks * NVECS);                         \
> +  ADJUST_NUNITS (VH##HF, riscv_vector_chunks * NVECS * 4);                     \
> +  ADJUST_NUNITS (VS##SF, riscv_vector_chunks * NVECS * 2);                     \
> +  ADJUST_NUNITS (VD##DF, riscv_vector_chunks * NVECS);                         \
> +                                                                               \
> +  ADJUST_ALIGNMENT (VB##QI, 1);                                                \
> +  ADJUST_ALIGNMENT (VH##HI, 2);                                                \
> +  ADJUST_ALIGNMENT (VS##SI, 4);                                                \
> +  ADJUST_ALIGNMENT (VD##DI, 8);                                                \
> +  ADJUST_ALIGNMENT (VH##HF, 2);                                                \
> +  ADJUST_ALIGNMENT (VS##SF, 4);                                                \
> +  ADJUST_ALIGNMENT (VD##DF, 8);
> +
> +/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
> +   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1DImode and VNx1DFmode.  */
> +VECTOR_MODE_WITH_PREFIX (VNx, INT, DI, 1, 0);
> +VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, DF, 1, 0);
> +RVV_MODES (1, VNx8, VNx4, VNx2, VNx1)
> +RVV_MODES (2, VNx16, VNx8, VNx4, VNx2)
> +RVV_MODES (4, VNx32, VNx16, VNx8, VNx4)
> +RVV_MODES (8, VNx64, VNx32, VNx16, VNx8)
> +
> +VECTOR_MODES_WITH_PREFIX (VNx, INT, 4, 0);
> +VECTOR_MODES_WITH_PREFIX (VNx, FLOAT, 4, 0);
> +ADJUST_NUNITS (VNx4QI, riscv_vector_chunks * 4);
> +ADJUST_NUNITS (VNx2HI, riscv_vector_chunks * 2);
> +ADJUST_NUNITS (VNx2HF, riscv_vector_chunks * 2);
> +ADJUST_ALIGNMENT (VNx4QI, 1);
> +ADJUST_ALIGNMENT (VNx2HI, 2);
> +ADJUST_ALIGNMENT (VNx2HF, 2);
> +
> +/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
> +   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1SImode and VNx1SFmode.  */
> +VECTOR_MODE_WITH_PREFIX (VNx, INT, SI, 1, 0);
> +VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, SF, 1, 0);
> +ADJUST_NUNITS (VNx1SI, riscv_vector_chunks);
> +ADJUST_NUNITS (VNx1SF, riscv_vector_chunks);
> +ADJUST_ALIGNMENT (VNx1SI, 4);
> +ADJUST_ALIGNMENT (VNx1SF, 4);
> +
> +VECTOR_MODES_WITH_PREFIX (VNx, INT, 2, 0);
> +ADJUST_NUNITS (VNx2QI, riscv_vector_chunks * 2);
> +ADJUST_ALIGNMENT (VNx2QI, 1);
> +
> +/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
> +   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1HImode and VNx1HFmode.  */
> +VECTOR_MODE_WITH_PREFIX (VNx, INT, HI, 1, 0);
> +VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, HF, 1, 0);
> +ADJUST_NUNITS (VNx1HI, riscv_vector_chunks);
> +ADJUST_NUNITS (VNx1HF, riscv_vector_chunks);
> +ADJUST_ALIGNMENT (VNx1HI, 2);
> +ADJUST_ALIGNMENT (VNx1HF, 2);
> +
> +/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
> +   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1QImode.  */
> +VECTOR_MODE_WITH_PREFIX (VNx, INT, QI, 1, 0);
> +ADJUST_NUNITS (VNx1QI, riscv_vector_chunks);
> +ADJUST_ALIGNMENT (VNx1QI, 1);
> +
>  /* TODO: According to RISC-V 'V' ISA spec, the maximun vector length can
>     be 65536 for a single vector register which means the vector mode in
>     GCC can be maximum = 65536 * 8 bits (LMUL=8).
> --
> 2.36.1
>

^ permalink raw reply	[flat|nested] 3+ messages in thread

* [PATCH] RISC-V: Add RVV machine modes.
@ 2022-09-15  8:41 juzhe.zhong
  0 siblings, 0 replies; 3+ messages in thread
From: juzhe.zhong @ 2022-09-15  8:41 UTC (permalink / raw)
  To: gcc-patches; +Cc: kito.cheng, palmer, zhongjuzhe

From: zhongjuzhe <juzhe.zhong@rivai.ai>

gcc/ChangeLog:

        * config/riscv/riscv-modes.def (VECTOR_BOOL_MODE): Define RVV mask modes.
        (ADJUST_NUNITS): Adjust NUNITS using riscv_vector_chunks.
        (ADJUST_ALIGNMENT): Adjust alignment.
        (ADJUST_BYTESIZE): Adjust bytesize.
        (RVV_MODES): New macro.
        (VECTOR_MODE_WITH_PREFIX): Define RVV vector modes.
        (VECTOR_MODES_WITH_PREFIX): Define RVV vector modes.
        (NUM_POLY_INT_COEFFS): remove redundant space.

---
 gcc/config/riscv/riscv-modes.def | 143 ++++++++++++++++++++++++++++++-
 1 file changed, 142 insertions(+), 1 deletion(-)

diff --git a/gcc/config/riscv/riscv-modes.def b/gcc/config/riscv/riscv-modes.def
index 6e30c1a5595..649dc5877d2 100644
--- a/gcc/config/riscv/riscv-modes.def
+++ b/gcc/config/riscv/riscv-modes.def
@@ -22,6 +22,147 @@ along with GCC; see the file COPYING3.  If not see
 FLOAT_MODE (HF, 2, ieee_half_format);
 FLOAT_MODE (TF, 16, ieee_quad_format);
 
+/* Vector modes.  */
+
+/* Encode the ratio of SEW/LMUL into the mask types. There are the following
+ * mask types.  */
+
+/* | Mode     | MIN_VLEN = 32 | MIN_VLEN = 64 |
+   |          | SEW/LMUL      | SEW/LMUL      |
+   | VNx1BI   | 32            | 64            |
+   | VNx2BI   | 16            | 32            |
+   | VNx4BI   | 8             | 16            |
+   | VNx8BI   | 4             | 8             |
+   | VNx16BI  | 2             | 4             |
+   | VNx32BI  | 1             | 2             |
+   | VNx64BI  | N/A           | 1             |  */
+
+VECTOR_BOOL_MODE (VNx1BI, 1, BI, 8);
+VECTOR_BOOL_MODE (VNx2BI, 2, BI, 8);
+VECTOR_BOOL_MODE (VNx4BI, 4, BI, 8);
+VECTOR_BOOL_MODE (VNx8BI, 8, BI, 8);
+VECTOR_BOOL_MODE (VNx16BI, 16, BI, 8);
+VECTOR_BOOL_MODE (VNx32BI, 32, BI, 8);
+VECTOR_BOOL_MODE (VNx64BI, 64, BI, 8);
+
+ADJUST_NUNITS (VNx1BI, riscv_vector_chunks * 1);
+ADJUST_NUNITS (VNx2BI, riscv_vector_chunks * 2);
+ADJUST_NUNITS (VNx4BI, riscv_vector_chunks * 4);
+ADJUST_NUNITS (VNx8BI, riscv_vector_chunks * 8);
+ADJUST_NUNITS (VNx16BI, riscv_vector_chunks * 16);
+ADJUST_NUNITS (VNx32BI, riscv_vector_chunks * 32);
+ADJUST_NUNITS (VNx64BI, riscv_vector_chunks * 64);
+
+ADJUST_ALIGNMENT (VNx1BI, 1);
+ADJUST_ALIGNMENT (VNx2BI, 1);
+ADJUST_ALIGNMENT (VNx4BI, 1);
+ADJUST_ALIGNMENT (VNx8BI, 1);
+ADJUST_ALIGNMENT (VNx16BI, 1);
+ADJUST_ALIGNMENT (VNx32BI, 1);
+ADJUST_ALIGNMENT (VNx64BI, 1);
+
+ADJUST_BYTESIZE (VNx1BI, riscv_vector_chunks *riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx2BI, riscv_vector_chunks *riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx4BI, riscv_vector_chunks *riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx8BI, riscv_vector_chunks *riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx16BI, riscv_vector_chunks *riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx32BI, riscv_vector_chunks *riscv_bytes_per_vector_chunk);
+ADJUST_BYTESIZE (VNx64BI, riscv_vector_chunks *riscv_bytes_per_vector_chunk);
+
+/*
+   | Mode        | MIN_VLEN=32 | MIN_VLEN=32 | MIN_VLEN=64 | MIN_VLEN=64 |
+   |             | LMUL        |  SEW/LMUL   | LMUL        | SEW/LMUL    |
+   | VNx1QI      | MF4         |  32         | MF8         | 64          |
+   | VNx2QI      | MF2         |  16         | MF4         | 32          |
+   | VNx4QI      | M1          |  8          | MF2         | 16          |
+   | VNx8QI      | M2          |  4          | M1          | 8           |
+   | VNx16QI     | M4          |  2          | M2          | 4           |
+   | VNx32QI     | M8          |  1          | M4          | 2           |
+   | VNx64QI     | N/A         |  N/A        | M8          | 1           |
+   | VNx1(HI|HF) | MF2         |  32         | MF4         | 64          |
+   | VNx2(HI|HF) | M1          |  16         | MF2         | 32          |
+   | VNx4(HI|HF) | M2          |  8          | M1          | 16          |
+   | VNx8(HI|HF) | M4          |  4          | M2          | 8           |
+   | VNx16(HI|HF)| M8          |  2          | M4          | 4           |
+   | VNx32(HI|HF)| N/A         |  N/A        | M8          | 2           |
+   | VNx1(SI|SF) | M1          |  32         | MF2         | 64          |
+   | VNx2(SI|SF) | M2          |  16         | M1          | 32          |
+   | VNx4(SI|SF) | M4          |  8          | M2          | 16          |
+   | VNx8(SI|SF) | M8          |  4          | M4          | 8           |
+   | VNx16(SI|SF)| N/A         |  N/A        | M8          | 4           |
+   | VNx1(DI|DF) | N/A         |  N/A        | M1          | 64          |
+   | VNx2(DI|DF) | N/A         |  N/A        | M2          | 32          |
+   | VNx4(DI|DF) | N/A         |  N/A        | M4          | 16          |
+   | VNx8(DI|DF) | N/A         |  N/A        | M8          | 8           |
+*/
+
+/* Define RVV modes whose sizes are multiples of 64-bit chunks.  */
+#define RVV_MODES(NVECS, VB, VH, VS, VD)                                       \
+  VECTOR_MODES_WITH_PREFIX (VNx, INT, 8 * NVECS, 0);                           \
+  VECTOR_MODES_WITH_PREFIX (VNx, FLOAT, 8 * NVECS, 0);                         \
+                                                                               \
+  ADJUST_NUNITS (VB##QI, riscv_vector_chunks *NVECS * 8);                      \
+  ADJUST_NUNITS (VH##HI, riscv_vector_chunks *NVECS * 4);                      \
+  ADJUST_NUNITS (VS##SI, riscv_vector_chunks *NVECS * 2);                      \
+  ADJUST_NUNITS (VD##DI, riscv_vector_chunks *NVECS);                          \
+  ADJUST_NUNITS (VH##HF, riscv_vector_chunks *NVECS * 4);                      \
+  ADJUST_NUNITS (VS##SF, riscv_vector_chunks *NVECS * 2);                      \
+  ADJUST_NUNITS (VD##DF, riscv_vector_chunks *NVECS);                          \
+                                                                               \
+  ADJUST_ALIGNMENT (VB##QI, 1);                                                \
+  ADJUST_ALIGNMENT (VH##HI, 2);                                                \
+  ADJUST_ALIGNMENT (VS##SI, 4);                                                \
+  ADJUST_ALIGNMENT (VD##DI, 8);                                                \
+  ADJUST_ALIGNMENT (VH##HF, 2);                                                \
+  ADJUST_ALIGNMENT (VS##SF, 4);                                                \
+  ADJUST_ALIGNMENT (VD##DF, 8);
+
+/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
+   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1DImode and VNx1DFmode.  */
+VECTOR_MODE_WITH_PREFIX (VNx, INT, DI, 1, 0);
+VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, DF, 1, 0);
+RVV_MODES (1, VNx8, VNx4, VNx2, VNx1)
+RVV_MODES (2, VNx16, VNx8, VNx4, VNx2)
+RVV_MODES (4, VNx32, VNx16, VNx8, VNx4)
+RVV_MODES (8, VNx64, VNx32, VNx16, VNx8)
+
+VECTOR_MODES_WITH_PREFIX (VNx, INT, 4, 0);
+VECTOR_MODES_WITH_PREFIX (VNx, FLOAT, 4, 0);
+ADJUST_NUNITS (VNx4QI, riscv_vector_chunks * 4);
+ADJUST_NUNITS (VNx2HI, riscv_vector_chunks * 2);
+ADJUST_NUNITS (VNx2HF, riscv_vector_chunks * 2);
+ADJUST_ALIGNMENT (VNx4QI, 1);
+ADJUST_ALIGNMENT (VNx2HI, 2);
+ADJUST_ALIGNMENT (VNx2HF, 2);
+
+/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
+   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1SImode and VNx1SFmode.  */
+VECTOR_MODE_WITH_PREFIX (VNx, INT, SI, 1, 0);
+VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, SF, 1, 0);
+ADJUST_NUNITS (VNx1SI, riscv_vector_chunks);
+ADJUST_NUNITS (VNx1SF, riscv_vector_chunks);
+ADJUST_ALIGNMENT (VNx1SI, 4);
+ADJUST_ALIGNMENT (VNx1SF, 4);
+
+VECTOR_MODES_WITH_PREFIX (VNx, INT, 2, 0);
+ADJUST_NUNITS (VNx2QI, riscv_vector_chunks * 2);
+ADJUST_ALIGNMENT (VNx2QI, 1);
+
+/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
+   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1HImode and VNx1HFmode.  */
+VECTOR_MODE_WITH_PREFIX (VNx, INT, HI, 1, 0);
+VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, HF, 1, 0);
+ADJUST_NUNITS (VNx1HI, riscv_vector_chunks);
+ADJUST_NUNITS (VNx1HF, riscv_vector_chunks);
+ADJUST_ALIGNMENT (VNx1HI, 2);
+ADJUST_ALIGNMENT (VNx1HF, 2);
+
+/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
+   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1QImode.  */
+VECTOR_MODE_WITH_PREFIX (VNx, INT, QI, 1, 0);
+ADJUST_NUNITS (VNx1QI, riscv_vector_chunks);
+ADJUST_ALIGNMENT (VNx1QI, 1);
+
 /* TODO: According to RISC-V 'V' ISA spec, the maximun vector length can
    be 65536 for a single vector register which means the vector mode in
    GCC can be maximum = 65536 * 8 bits (LMUL=8).
@@ -33,4 +174,4 @@ FLOAT_MODE (TF, 16, ieee_quad_format);
 
 /* Coefficient 1 is multiplied by the number of 64-bit/32-bit chunks in a vector
    minus one.  */
-#define NUM_POLY_INT_COEFFS 2
+#define NUM_POLY_INT_COEFFS 2
\ No newline at end of file
-- 
2.36.1


^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2022-09-23 15:45 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-09-15 11:39 [PATCH] RISC-V: Add RVV machine modes juzhe.zhong
2022-09-23 15:45 ` Kito Cheng
  -- strict thread matches above, loose matches on Subject: below --
2022-09-15  8:41 juzhe.zhong

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).